Learning and tuning fuzzy logic controllers through reinforcements
- PMID:18276471
- DOI: 10.1109/72.159061
Learning and tuning fuzzy logic controllers through reinforcements
Abstract
A method for learning and tuning a fuzzy logic controller based on reinforcements from a dynamic system is presented. It is shown that: the generalized approximate-reasoning-based intelligent control (GARIC) architecture learns and tunes a fuzzy logic controller even when only weak reinforcement, such as a binary failure signal, is available; introduces a new conjunction operator in computing the rule strengths of fuzzy control rules; introduces a new localized mean of maximum (LMOM) method in combining the conclusions of several firing control rules; and learns to produce real-valued control actions. Learning is achieved by integrating fuzzy inference into a feedforward network, which can then adaptively improve performance by using gradient descent methods. The GARIC architecture is applied to a cart-pole balancing system and demonstrates significant improvements in terms of the speed of learning and robustness to changes in the dynamic system's parameters over previous schemes for cart-pole balancing.
Similar articles
- Genetic reinforcement learning through symbiotic evolution for fuzzy controller design.Juang CF, Lin JY, Lin CT.Juang CF, et al.IEEE Trans Syst Man Cybern B Cybern. 2000;30(2):290-302. doi: 10.1109/3477.836377.IEEE Trans Syst Man Cybern B Cybern. 2000.PMID:18244755
- Fuzzy-rule emulated networks, based on reinforcement learning for nonlinear discrete-time controllers.Treesatayapun C.Treesatayapun C.ISA Trans. 2008 Oct;47(4):362-73. doi: 10.1016/j.isatra.2008.07.001.ISA Trans. 2008.PMID:18675416
- Compensatory neurofuzzy systems with fast learning algorithms.Zhang YQ, Kandel A.Zhang YQ, et al.IEEE Trans Neural Netw. 1998;9(1):83-105. doi: 10.1109/72.655032.IEEE Trans Neural Netw. 1998.PMID:18252432
- Fuzzy logic systems and medical applications.Vlamou E, Papadopoulos B.Vlamou E, et al.AIMS Neurosci. 2019 Oct 22;6(4):266-272. doi: 10.3934/Neuroscience.2019.4.266. eCollection 2019.AIMS Neurosci. 2019.PMID:32341982Free PMC article.Review.
- A fuzzy logic controller.Yamakawa T.Yamakawa T.J Biotechnol. 1992 Jun;24(1):1-32. doi: 10.1016/0168-1656(92)90059-i.J Biotechnol. 1992.PMID:1368349Review.
Cited by
- Interacting Learning Processes during Skill Acquisition: Learning to control with gradually changing system dynamics.Ludolph N, Giese MA, Ilg W.Ludolph N, et al.Sci Rep. 2017 Oct 16;7(1):13191. doi: 10.1038/s41598-017-13510-0.Sci Rep. 2017.PMID:29038562Free PMC article.Clinical Trial.
- Defining the plasticity of transcription factor binding sites by Deconstructing DNA consensus sequences: the PhoP-binding sites among gamma/enterobacteria.Harari O, Park SY, Huang H, Groisman EA, Zwir I.Harari O, et al.PLoS Comput Biol. 2010 Jul 22;6(7):e1000862. doi: 10.1371/journal.pcbi.1000862.PLoS Comput Biol. 2010.PMID:20661307Free PMC article.
- Efficient Actor-Critic Algorithm with Hierarchical Model Learning and Planning.Zhong S, Liu Q, Fu Q.Zhong S, et al.Comput Intell Neurosci. 2016;2016:4824072. doi: 10.1155/2016/4824072. Epub 2016 Oct 3.Comput Intell Neurosci. 2016.PMID:27795704Free PMC article.
- Adaptive fuzzy control of electrically stimulated muscles for arm movements.Micera S, Sabatini AM, Dario P.Micera S, et al.Med Biol Eng Comput. 1999 Nov;37(6):680-5. doi: 10.1007/BF02513367.Med Biol Eng Comput. 1999.PMID:10723872
LinkOut - more resources
Full Text Sources
Other Literature Sources